[PATCH v5 4/8] virtio-user: add vhost adapter layer

[Jianfeng Tan <jianfeng.tan@intel.com>]

This patch is to provide vhost adapter layer implementations. Instead
of relying on a hypervisor to translate between device emulation and
vhost backend, here we directly talk with vhost backend through the
vhost file. Depending on the type of vhost file,
  - vhost-user is used if the given path points to a unix socket;
  - vhost-kernel is used if the given path points to a char device.

Here three main APIs are provided to upper layer (device emulation):
  - vhost_user_setup(), to set up env to talk to a vhost user backend;
  - vhost_kernel_setup(), to set up env to talk to a vhost kernel backend.
  - vhost_call(), to provide a unified interface to communicate with
    vhost backend.

  ----------------------
  | ------------------ |
  | | virtio driver  | |
  | ------------------ |
  |         |          |
  | ------------------ | ------>  virtio-user PMD
  | | device emulate | |
  | |                | |
  | | vhost adapter  |-|----> (vhost_user.c, vhost_kernel.c, vhost.c)
  | ------------------ |
  ----------------------
            |
            | -------------- --> (vhost-user protocol or vhost-net ioctls)
            |
   ------------------
   | vhost backend  |
   ------------------

Signed-off-by: Huawei Xie <huawei.xie@intel.com>
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
---
 config/common_linuxapp                        |   3 +
 drivers/net/virtio/Makefile                   |   6 +
 drivers/net/virtio/virtio_user/vhost.c        | 105 +++++++
 drivers/net/virtio/virtio_user/vhost.h        | 222 +++++++++++++++
 drivers/net/virtio/virtio_user/vhost_kernel.c | 254 +++++++++++++++++
 drivers/net/virtio/virtio_user/vhost_user.c   | 378 ++++++++++++++++++++++++++
 6 files changed, 968 insertions(+)
 create mode 100644 drivers/net/virtio/virtio_user/vhost.c
 create mode 100644 drivers/net/virtio/virtio_user/vhost.h
 create mode 100644 drivers/net/virtio/virtio_user/vhost_kernel.c
 create mode 100644 drivers/net/virtio/virtio_user/vhost_user.c

diff --git a/config/common_linuxapp b/config/common_linuxapp
index 7e698e2..946a6d4 100644
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -43,3 +43,6 @@ CONFIG_RTE_LIBRTE_VHOST=y
 CONFIG_RTE_LIBRTE_PMD_VHOST=y
 CONFIG_RTE_LIBRTE_PMD_AF_PACKET=y
 CONFIG_RTE_LIBRTE_POWER=y
+
+# Enable virtio-user
+CONFIG_RTE_VIRTIO_VDEV=y
diff --git a/drivers/net/virtio/Makefile b/drivers/net/virtio/Makefile
index ef84f60..c9f2bc0 100644
--- a/drivers/net/virtio/Makefile
+++ b/drivers/net/virtio/Makefile
@@ -55,6 +55,12 @@ ifeq ($(findstring RTE_MACHINE_CPUFLAG_SSSE3,$(CFLAGS)),RTE_MACHINE_CPUFLAG_SSSE
 SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_rxtx_simple.c
 endif
 
+ifeq ($(CONFIG_RTE_VIRTIO_VDEV),y)
+SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_user/vhost.c
+SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_user/vhost_user.c
+SRCS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += virtio_user/vhost_kernel.c
+endif
+
 # this lib depends upon:
 DEPDIRS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += lib/librte_eal lib/librte_ether
 DEPDIRS-$(CONFIG_RTE_LIBRTE_VIRTIO_PMD) += lib/librte_mempool lib/librte_mbuf
diff --git a/drivers/net/virtio/virtio_user/vhost.c b/drivers/net/virtio/virtio_user/vhost.c
new file mode 100644
index 0000000..1944a97
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost.c
@@ -0,0 +1,105 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "vhost.h"
+
+static const char * const vhost_msg_strings[] = {
+	[VHOST_MSG_SET_OWNER] = "VHOST_MSG_SET_OWNER",
+	[VHOST_MSG_RESET_OWNER] = "VHOST_MSG_RESET_OWNER",
+	[VHOST_MSG_SET_FEATURES] = "VHOST_MSG_SET_FEATURES",
+	[VHOST_MSG_GET_FEATURES] = "VHOST_MSG_GET_FEATURES",
+	[VHOST_MSG_SET_VRING_CALL] = "VHOST_MSG_SET_VRING_CALL",
+	[VHOST_MSG_SET_VRING_NUM] = "VHOST_MSG_SET_VRING_NUM",
+	[VHOST_MSG_SET_VRING_BASE] = "VHOST_MSG_SET_VRING_BASE",
+	[VHOST_MSG_GET_VRING_BASE] = "VHOST_MSG_GET_VRING_BASE",
+	[VHOST_MSG_SET_VRING_ADDR] = "VHOST_MSG_SET_VRING_ADDR",
+	[VHOST_MSG_SET_VRING_KICK] = "VHOST_MSG_SET_VRING_KICK",
+	[VHOST_MSG_SET_MEM_TABLE] = "VHOST_MSG_SET_MEM_TABLE",
+	NULL,
+};
+
+static uint64_t vhost_req_map[][2] = {
+	[VHOST_MSG_SET_OWNER] = {
+		VHOST_SET_OWNER, VHOST_USER_SET_OWNER
+	},
+	[VHOST_MSG_RESET_OWNER] = {
+		VHOST_RESET_OWNER, VHOST_USER_RESET_OWNER
+	},
+	[VHOST_MSG_SET_FEATURES] = {
+		VHOST_SET_FEATURES, VHOST_USER_SET_FEATURES
+	},
+	[VHOST_MSG_GET_FEATURES] = {
+		VHOST_GET_FEATURES, VHOST_USER_GET_FEATURES
+	},
+	[VHOST_MSG_SET_VRING_CALL] = {
+		VHOST_SET_VRING_CALL, VHOST_USER_SET_VRING_CALL
+	},
+	[VHOST_MSG_SET_VRING_NUM] = {
+		VHOST_SET_VRING_NUM, VHOST_USER_SET_VRING_NUM
+	},
+	[VHOST_MSG_SET_VRING_BASE] = {
+		VHOST_SET_VRING_BASE, VHOST_USER_SET_VRING_BASE
+	},
+	[VHOST_MSG_GET_VRING_BASE] = {
+		VHOST_GET_VRING_BASE, VHOST_USER_GET_VRING_BASE
+	},
+	[VHOST_MSG_SET_VRING_ADDR] = {
+		VHOST_SET_VRING_ADDR, VHOST_USER_SET_VRING_ADDR
+	},
+	[VHOST_MSG_SET_VRING_KICK] = {
+		VHOST_SET_VRING_KICK, VHOST_USER_SET_VRING_KICK
+	},
+	[VHOST_MSG_SET_MEM_TABLE] = {
+		VHOST_SET_MEM_TABLE, VHOST_USER_SET_MEM_TABLE
+	},
+};
+
+int
+vhost_call(int vhostfd, int type, uint64_t req, void *arg)
+{
+	uint64_t req_new;
+	int ret;
+
+	PMD_DRV_LOG(INFO, "%s", vhost_msg_strings[req]);
+
+	req_new = vhost_req_map[req][type];
+	if (type == VHOST_USER)
+		ret = vhost_user_sock(vhostfd, req_new, arg);
+	else
+		ret = vhost_kernel_ioctl(vhostfd, req_new, arg);
+
+	if (ret < 0)
+		PMD_DRV_LOG(ERR, "vhost_call %s failed: %s\n",
+			    vhost_msg_strings[req], strerror(errno));
+	return ret;
+}
diff --git a/drivers/net/virtio/virtio_user/vhost.h b/drivers/net/virtio/virtio_user/vhost.h
new file mode 100644
index 0000000..6bac1e8
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost.h
@@ -0,0 +1,222 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _VHOST_NET_USER_H
+#define _VHOST_NET_USER_H
+
+#include <stdint.h>
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#include "../virtio_pci.h"
+#include "../virtio_logs.h"
+#include "../virtqueue.h"
+
+#define VHOST_MEMORY_MAX_NREGIONS 8
+
+struct vhost_vring_state {
+	unsigned int index;
+	unsigned int num;
+};
+
+struct vhost_vring_file {
+	unsigned int index;
+	int fd;
+};
+
+struct vhost_vring_addr {
+	unsigned int index;
+	/* Option flags. */
+	unsigned int flags;
+	/* Flag values: */
+	/* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+	/* Start of array of descriptors (virtually contiguous) */
+	uint64_t desc_user_addr;
+	/* Used structure address. Must be 32 bit aligned */
+	uint64_t used_user_addr;
+	/* Available structure address. Must be 16 bit aligned */
+	uint64_t avail_user_addr;
+	/* Logging support. */
+	/* Log writes to used structure, at offset calculated from specified
+	 * address. Address must be 32 bit aligned.
+	 */
+	uint64_t log_guest_addr;
+};
+
+enum vhost_user_request {
+	VHOST_USER_NONE = 0,
+	VHOST_USER_GET_FEATURES = 1,
+	VHOST_USER_SET_FEATURES = 2,
+	VHOST_USER_SET_OWNER = 3,
+	VHOST_USER_RESET_OWNER = 4,
+	VHOST_USER_SET_MEM_TABLE = 5,
+	VHOST_USER_SET_LOG_BASE = 6,
+	VHOST_USER_SET_LOG_FD = 7,
+	VHOST_USER_SET_VRING_NUM = 8,
+	VHOST_USER_SET_VRING_ADDR = 9,
+	VHOST_USER_SET_VRING_BASE = 10,
+	VHOST_USER_GET_VRING_BASE = 11,
+	VHOST_USER_SET_VRING_KICK = 12,
+	VHOST_USER_SET_VRING_CALL = 13,
+	VHOST_USER_SET_VRING_ERR = 14,
+	VHOST_USER_GET_PROTOCOL_FEATURES = 15,
+	VHOST_USER_SET_PROTOCOL_FEATURES = 16,
+	VHOST_USER_GET_QUEUE_NUM = 17,
+	VHOST_USER_SET_VRING_ENABLE = 18,
+	VHOST_USER_MAX
+};
+
+struct vhost_memory_region {
+	uint64_t guest_phys_addr;
+	uint64_t memory_size; /* bytes */
+	uint64_t userspace_addr;
+	uint64_t mmap_offset;
+};
+
+struct vhost_memory_kernel {
+	uint32_t nregions;
+	uint32_t padding;
+	struct vhost_memory_region regions[0];
+};
+
+struct vhost_memory {
+	uint32_t nregions;
+	uint32_t padding;
+	struct vhost_memory_region regions[VHOST_MEMORY_MAX_NREGIONS];
+};
+
+struct vhost_user_msg {
+	enum vhost_user_request request;
+
+#define VHOST_USER_VERSION_MASK     0x3
+#define VHOST_USER_REPLY_MASK       (0x1 << 2)
+	uint32_t flags;
+	uint32_t size; /* the following payload size */
+	union {
+#define VHOST_USER_VRING_IDX_MASK   0xff
+#define VHOST_USER_VRING_NOFD_MASK  (0x1 << 8)
+		uint64_t u64;
+		struct vhost_vring_state state;
+		struct vhost_vring_addr addr;
+		struct vhost_memory memory;
+	} payload;
+	int fds[VHOST_MEMORY_MAX_NREGIONS];
+} __attribute((packed));
+
+#define VHOST_USER_HDR_SIZE offsetof(struct vhost_user_msg, payload.u64)
+#define VHOST_USER_PAYLOAD_SIZE \
+	(sizeof(struct vhost_user_msg) - VHOST_USER_HDR_SIZE)
+
+/* The version of the protocol we support */
+#define VHOST_USER_VERSION    0x1
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory_kernel)
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/*****************************************************************************/
+
+/* Ioctl defines */
+#define TUNSETIFF     _IOW('T', 202, int)
+#define TUNGETFEATURES _IOR('T', 207, unsigned int)
+#define TUNSETOFFLOAD  _IOW('T', 208, unsigned int)
+#define TUNGETIFF      _IOR('T', 210, unsigned int)
+#define TUNSETSNDBUF   _IOW('T', 212, int)
+#define TUNGETVNETHDRSZ _IOR('T', 215, int)
+#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE  _IOW('T', 217, int)
+#define TUNSETVNETLE _IOW('T', 220, int)
+#define TUNSETVNETBE _IOW('T', 222, int)
+
+/* TUNSETIFF ifr flags */
+#define IFF_TAP          0x0002
+#define IFF_NO_PI        0x1000
+#define IFF_ONE_QUEUE    0x2000
+#define IFF_VNET_HDR     0x4000
+#define IFF_MULTI_QUEUE  0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
+
+/* Features for GSO (TUNSETOFFLOAD). */
+#define TUN_F_CSUM	0x01	/* You can hand me unchecksummed packets. */
+#define TUN_F_TSO4	0x02	/* I can handle TSO for IPv4 packets */
+#define TUN_F_TSO6	0x04	/* I can handle TSO for IPv6 packets */
+#define TUN_F_TSO_ECN	0x08	/* I can handle TSO with ECN bits. */
+#define TUN_F_UFO	0x10	/* I can handle UFO packets */
+
+enum {
+	VHOST_MSG_SET_OWNER,
+	VHOST_MSG_RESET_OWNER,
+	VHOST_MSG_SET_FEATURES,
+	VHOST_MSG_GET_FEATURES,
+	VHOST_MSG_SET_VRING_CALL,
+	VHOST_MSG_SET_VRING_NUM,
+	VHOST_MSG_SET_VRING_BASE,
+	VHOST_MSG_GET_VRING_BASE,
+	VHOST_MSG_SET_VRING_ADDR,
+	VHOST_MSG_SET_VRING_KICK,
+	VHOST_MSG_SET_MEM_TABLE,
+	VHOST_MSG_MAX,
+};
+
+#define VHOST_KERNEL	0
+#define VHOST_USER	1
+
+int vhost_user_sock(int vhostfd, uint64_t req, void *arg);
+int vhost_user_setup(const char *path);
+
+int vhost_kernel_ioctl(int vhostfd, uint64_t req, void *arg);
+int vhost_kernel_setup(const char *path, const char *ifname, int *p_tapfd);
+int vhost_kernel_post(int vhostfd, int tapfd, uint64_t features, uint32_t nvqs);
+
+int vhost_call(int vhostfd, int type, uint64_t req, void *arg);
+
+#endif
diff --git a/drivers/net/virtio/virtio_user/vhost_kernel.c b/drivers/net/virtio/virtio_user/vhost_kernel.c
new file mode 100644
index 0000000..41196cf
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost_kernel.c
@@ -0,0 +1,254 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <net/if.h>
+#include <string.h>
+#include <errno.h>
+
+#include <rte_memory.h>
+#include <rte_eal_memconfig.h>
+
+#include "vhost.h"
+
+#define TUN_DEF_SNDBUF	(1ull << 20)
+#define PATH_NET_TUN	"/dev/net/tun"
+
+/** Merge those virtually adjacent memsegs into one region.
+ */
+static void
+prepare_vhost_memory_kernel(struct vhost_memory_kernel **p_vm)
+{
+	uint32_t i, j, k = 0;
+	struct rte_memseg *seg;
+	struct vhost_memory_region *mr;
+	struct vhost_memory_kernel *vm;
+
+	vm = malloc(sizeof(struct vhost_memory_kernel) +
+		    RTE_MAX_MEMSEG * sizeof(struct vhost_memory_region));
+
+	for (i = 0; i < RTE_MAX_MEMSEG; ++i) {
+		seg = &rte_eal_get_configuration()->mem_config->memseg[i];
+		if (!seg->addr)
+			break;
+
+		int new_region = 1;
+
+		for (j = 0; j < k; ++j) {
+			mr = &vm->regions[j];
+
+			if (mr->userspace_addr + mr->memory_size ==
+			    (uint64_t)seg->addr) {
+				mr->memory_size += seg->len;
+				new_region = 0;
+				break;
+			}
+
+			if ((uint64_t)seg->addr + seg->len ==
+			    mr->userspace_addr) {
+				mr->guest_phys_addr = (uint64_t)seg->addr;
+				mr->userspace_addr = (uint64_t)seg->addr;
+				mr->memory_size += seg->len;
+				new_region = 0;
+				break;
+			}
+		}
+
+		if (new_region == 0)
+			continue;
+
+		mr = &vm->regions[k++];
+		mr->guest_phys_addr = (uint64_t)seg->addr; /* use vaddr here! */
+		mr->userspace_addr = (uint64_t)seg->addr;
+		mr->memory_size = seg->len;
+		mr->mmap_offset = 0;
+	}
+
+	vm->nregions = k;
+	vm->padding = 0;
+	*p_vm = vm;
+}
+
+int
+vhost_kernel_ioctl(int vhostfd, uint64_t req, void *arg)
+{
+	int ret;
+	struct vhost_memory_kernel *vm = NULL;
+
+	if (req == VHOST_SET_MEM_TABLE) {
+		prepare_vhost_memory_kernel(&vm);
+		arg = (void *)vm;
+	}
+
+	ret = ioctl(vhostfd, req, arg);
+
+	if (req == VHOST_SET_MEM_TABLE)
+		free(vm);
+
+	return ret;
+}
+
+/**
+ * Set up environment to talk with a vhost kernel backend.
+ * @param path
+ *   - The path to vhost net (kernel) character file.
+ *
+ * @param ifname
+ *   - Specify the tap device name if any, or NULL.
+ *
+ * @param p_tapfd
+ *   - Pointer to store the fd of tap device.
+ *
+ * @return
+ *   - (-1) if fail to set up;
+ *   - (>=0) if successful, and it is the fd to vhostfd.
+ */
+int
+vhost_kernel_setup(const char *path, const char *ifname, int *p_tapfd)
+{
+	int vhostfd, tapfd;
+	int len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	int req_mq = 0;
+	int sndbuf = TUN_DEF_SNDBUF;
+	unsigned int features;
+	struct ifreq ifr;
+
+	/* TODO:
+	 * 1. get/set offload capability, tap_probe_has_ufo, tap_fd_set_offload
+	 * 2. verify we can get/set vnet_hdr_len, tap_probe_vnet_hdr_len
+	 * 3. get number of memory regions from vhost module parameter
+	 * max_mem_regions, supported in newer version linux kernel
+	 */
+
+	tapfd = open(PATH_NET_TUN, O_RDWR);
+	if (tapfd < 0) {
+		PMD_DRV_LOG(ERR, "fail to open %s: %s",
+			    PATH_NET_TUN, strerror(errno));
+		return -1;
+	}
+
+	memset(&ifr, 0, sizeof(ifr));
+	ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
+
+	if (ioctl(tapfd, TUNGETFEATURES, &features) == -1) {
+		PMD_DRV_LOG(ERR, "TUNGETFEATURES failed: %s", strerror(errno));
+		goto error;
+	}
+
+	if (features & IFF_ONE_QUEUE)
+		ifr.ifr_flags |= IFF_ONE_QUEUE;
+
+	if (features & IFF_VNET_HDR)
+		ifr.ifr_flags |= IFF_VNET_HDR;
+	else {
+		PMD_DRV_LOG(ERR, "vnet_hdr not supported by kernel");
+		goto error;
+	}
+
+	if (req_mq) {
+		if (features & IFF_MULTI_QUEUE)
+			ifr.ifr_flags |= IFF_MULTI_QUEUE;
+		else {
+			PMD_DRV_LOG(ERR, "multiqueue not supported by kernel");
+			goto error;
+		}
+	}
+
+	if (ifname)
+		strncpy(ifr.ifr_name, ifname, IFNAMSIZ);
+	else
+		strncpy(ifr.ifr_name, "tap%d", IFNAMSIZ);
+	if (ioctl(tapfd, TUNSETIFF, (void *)&ifr) == -1) {
+		PMD_DRV_LOG(ERR, "TUNSETIFF failed: %s", strerror(errno));
+		goto error;
+	}
+	fcntl(tapfd, F_SETFL, O_NONBLOCK);
+
+	if (ioctl(tapfd, TUNSETVNETHDRSZ, &len) < 0) {
+		PMD_DRV_LOG(ERR, "TUNSETVNETHDRSZ failed: %s", strerror(errno));
+		goto error;
+	}
+
+	if (ioctl(tapfd, TUNSETSNDBUF, &sndbuf) < 0) {
+		PMD_DRV_LOG(ERR, "TUNSETSNDBUF failed: %s", strerror(errno));
+		goto error;
+	}
+
+	vhostfd = open(path, O_RDWR);
+	if (vhostfd < 0) {
+		PMD_DRV_LOG(ERR, "fail to open %s, %s", path, strerror(errno));
+		goto error;
+	}
+
+	*p_tapfd = tapfd;
+	return vhostfd;
+
+error:
+	close(tapfd);
+	return -1;
+}
+
+int
+vhost_kernel_post(int vhostfd, int tapfd, uint64_t features, uint32_t nvqs)
+{
+	struct vhost_vring_file f;
+	uint16_t hdr_size;
+	int ret;
+
+	if ((features & (1ULL << VIRTIO_NET_F_MRG_RXBUF)) ||
+	    (features & (1ULL << VIRTIO_F_VERSION_1)))
+		hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	else
+		hdr_size = sizeof(struct virtio_net_hdr);
+
+	if (ioctl(tapfd, TUNSETVNETHDRSZ, &hdr_size) == -1) {
+		PMD_DRV_LOG(ERR, "TUNSETVNETHDRSZ fails, %s", strerror(errno));
+		return -1;
+	}
+
+	f.fd = tapfd;
+	for (f.index = 0; f.index < nvqs; ++f.index) {
+		ret = vhost_kernel_ioctl(vhostfd, VHOST_NET_SET_BACKEND, &f);
+		if (ret < 0) {
+			PMD_DRV_LOG(ERR, "VHOST_NET_SET_BACKEND fails, %s",
+				    strerror(errno));
+			return -1;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/virtio/virtio_user/vhost_user.c b/drivers/net/virtio/virtio_user/vhost_user.c
new file mode 100644
index 0000000..b0a84cf
--- /dev/null
+++ b/drivers/net/virtio/virtio_user/vhost_user.c
@@ -0,0 +1,378 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
+ *   All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of Intel Corporation nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/un.h>
+#include <string.h>
+#include <errno.h>
+
+#include "vhost.h"
+
+static int
+vhost_user_write(int fd, void *buf, int len, int *fds, int fd_num)
+{
+	int r;
+	struct msghdr msgh;
+	struct iovec iov;
+	size_t fd_size = fd_num * sizeof(int);
+	char control[CMSG_SPACE(fd_size)];
+	struct cmsghdr *cmsg;
+
+	memset(&msgh, 0, sizeof(msgh));
+	memset(control, 0, sizeof(control));
+
+	iov.iov_base = (uint8_t *)buf;
+	iov.iov_len = len;
+
+	msgh.msg_iov = &iov;
+	msgh.msg_iovlen = 1;
+	msgh.msg_control = control;
+	msgh.msg_controllen = sizeof(control);
+
+	cmsg = CMSG_FIRSTHDR(&msgh);
+	cmsg->cmsg_len = CMSG_LEN(fd_size);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	memcpy(CMSG_DATA(cmsg), fds, fd_size);
+
+	do {
+		r = sendmsg(fd, &msgh, 0);
+	} while (r < 0 && errno == EINTR);
+
+	return r;
+}
+
+static int
+vhost_user_read(int fd, struct vhost_user_msg *msg)
+{
+	uint32_t valid_flags = VHOST_USER_REPLY_MASK | VHOST_USER_VERSION;
+	int ret, sz_hdr = VHOST_USER_HDR_SIZE, sz_payload;
+
+	ret = recv(fd, (void *)msg, sz_hdr, 0);
+	if (ret < sz_hdr) {
+		PMD_DRV_LOG(ERR, "Failed to recv msg hdr: %d instead of %d.",
+			    ret, sz_hdr);
+		goto fail;
+	}
+
+	/* validate msg flags */
+	if (msg->flags != (valid_flags)) {
+		PMD_DRV_LOG(ERR, "Failed to recv msg: flags %x instead of %x.",
+			    msg->flags, valid_flags);
+		goto fail;
+	}
+
+	sz_payload = msg->size;
+	if (sz_payload) {
+		ret = recv(fd, (void *)((char *)msg + sz_hdr), sz_payload, 0);
+		if (ret < sz_payload) {
+			PMD_DRV_LOG(ERR, "Failed to recv msg payload: %d instead of %d.",
+				    ret, msg->size);
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	return -1;
+}
+
+struct hugepage_file_info {
+	uint64_t addr;            /**< virtual addr */
+	size_t   size;            /**< the file size */
+	char     path[PATH_MAX];  /**< path to backing file */
+};
+
+/* Two possible options:
+ * 1. Match HUGEPAGE_INFO_FMT to find the file storing struct hugepage_file
+ * array. This is simple but cannot be used in secondary process because
+ * secondary process will close and munmap that file.
+ * 2. Match HUGEFILE_FMT to find hugepage files directly.
+ *
+ * We choose option 2.
+ */
+static int
+get_hugepage_file_info(struct hugepage_file_info huges[], int max)
+{
+	int idx;
+	FILE *f;
+	char buf[BUFSIZ], *tmp, *tail;
+	char *str_underline, *str_start;
+	int huge_index;
+	uint64_t v_start, v_end;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f) {
+		PMD_DRV_LOG(ERR, "cannot open /proc/self/maps");
+		return -1;
+	}
+
+	idx = 0;
+	while (fgets(buf, sizeof(buf), f) != NULL) {
+		if (sscanf(buf, "%" PRIx64 "-%" PRIx64, &v_start, &v_end) < 2) {
+			PMD_DRV_LOG(ERR, "Failed to parse address");
+			goto error;
+		}
+
+		tmp = strchr(buf, ' ') + 1; /** skip address */
+		tmp = strchr(tmp, ' ') + 1; /** skip perm */
+		tmp = strchr(tmp, ' ') + 1; /** skip offset */
+		tmp = strchr(tmp, ' ') + 1; /** skip dev */
+		tmp = strchr(tmp, ' ') + 1; /** skip inode */
+		while (*tmp == ' ')         /** skip spaces */
+			tmp++;
+		tail = strrchr(tmp, '\n');  /** remove newline if exists */
+		if (tail)
+			*tail = '\0';
+
+		/* Match HUGEFILE_FMT, aka "%s/%smap_%d",
+		 * which is defined in eal_filesystem.h
+		 */
+		str_underline = strrchr(tmp, '_');
+		if (!str_underline)
+			continue;
+
+		str_start = str_underline - strlen("map");
+		if (str_start < tmp)
+			continue;
+
+		if (sscanf(str_start, "map_%d", &huge_index) != 1)
+			continue;
+
+		if (idx >= max) {
+			PMD_DRV_LOG(ERR, "Exceed maximum of %d", max);
+			goto error;
+		}
+		huges[idx].addr = v_start;
+		huges[idx].size = v_end - v_start;
+		strcpy(huges[idx].path, tmp);
+		idx++;
+	}
+
+	fclose(f);
+	return idx;
+
+error:
+	fclose(f);
+	return -1;
+}
+
+static int
+prepare_vhost_memory_user(struct vhost_user_msg *msg, int fds[])
+{
+	int i, num;
+	struct hugepage_file_info huges[VHOST_MEMORY_MAX_NREGIONS];
+	struct vhost_memory_region *mr;
+
+	num = get_hugepage_file_info(huges, VHOST_MEMORY_MAX_NREGIONS);
+	if (num < 0) {
+		PMD_INIT_LOG(ERR, "Failed to prepare memory for vhost-user");
+		return -1;
+	}
+
+	for (i = 0; i < num; ++i) {
+		mr = &msg->payload.memory.regions[i];
+		mr->guest_phys_addr = huges[i].addr; /* use vaddr! */
+		mr->userspace_addr = huges[i].addr;
+		mr->memory_size = huges[i].size;
+		mr->mmap_offset = 0;
+		fds[i] = open(huges[i].path, O_RDWR);
+	}
+
+	msg->payload.memory.nregions = num;
+	msg->payload.memory.padding = 0;
+
+	return 0;
+}
+
+static struct vhost_user_msg m;
+
+int
+vhost_user_sock(int vhostfd, uint64_t req, void *arg)
+{
+	struct vhost_user_msg msg;
+	struct vhost_vring_file *file = 0;
+	int need_reply = 0;
+	int fds[VHOST_MEMORY_MAX_NREGIONS];
+	int fd_num = 0;
+	int i, len;
+
+	msg.request = req;
+	msg.flags = VHOST_USER_VERSION;
+	msg.size = 0;
+
+	switch (req) {
+	case VHOST_USER_GET_FEATURES:
+		need_reply = 1;
+		break;
+
+	case VHOST_USER_SET_FEATURES:
+	case VHOST_USER_SET_LOG_BASE:
+		msg.payload.u64 = *((__u64 *)arg);
+		msg.size = sizeof(m.payload.u64);
+		break;
+
+	case VHOST_USER_SET_OWNER:
+	case VHOST_USER_RESET_OWNER:
+		break;
+
+	case VHOST_USER_SET_MEM_TABLE:
+		if (prepare_vhost_memory_user(&msg, fds) < 0)
+			return -1;
+		fd_num = msg.payload.memory.nregions;
+		msg.size = sizeof(m.payload.memory.nregions);
+		msg.size += sizeof(m.payload.memory.padding);
+		msg.size += fd_num * sizeof(struct vhost_memory_region);
+		break;
+
+	case VHOST_USER_SET_LOG_FD:
+		fds[fd_num++] = *((int *)arg);
+		break;
+
+	case VHOST_USER_SET_VRING_NUM:
+	case VHOST_USER_SET_VRING_BASE:
+		memcpy(&msg.payload.state, arg, sizeof(msg.payload.state));
+		msg.size = sizeof(m.payload.state);
+		break;
+
+	case VHOST_USER_GET_VRING_BASE:
+		memcpy(&msg.payload.state, arg, sizeof(msg.payload.state));
+		msg.size = sizeof(m.payload.state);
+		need_reply = 1;
+		break;
+
+	case VHOST_USER_SET_VRING_ADDR:
+		memcpy(&msg.payload.addr, arg, sizeof(msg.payload.addr));
+		msg.size = sizeof(m.payload.addr);
+		break;
+
+	case VHOST_USER_SET_VRING_KICK:
+	case VHOST_USER_SET_VRING_CALL:
+	case VHOST_USER_SET_VRING_ERR:
+		file = arg;
+		msg.payload.u64 = file->index & VHOST_USER_VRING_IDX_MASK;
+		msg.size = sizeof(m.payload.u64);
+		if (file->fd > 0)
+			fds[fd_num++] = file->fd;
+		else
+			msg.payload.u64 |= VHOST_USER_VRING_NOFD_MASK;
+		break;
+
+	default:
+		PMD_DRV_LOG(ERR, "trying to send unhandled msg type");
+		return -1;
+	}
+
+	len = VHOST_USER_HDR_SIZE + msg.size;
+	if (vhost_user_write(vhostfd, &msg, len, fds, fd_num) < 0)
+		return 0;
+
+	if (req == VHOST_USER_SET_MEM_TABLE)
+		for (i = 0; i < fd_num; ++i)
+			close(fds[i]);
+
+	if (need_reply) {
+		if (vhost_user_read(vhostfd, &msg) < 0)
+			return -1;
+
+		if (req != msg.request) {
+			PMD_DRV_LOG(ERR, "Received unexpected msg type.");
+			return -1;
+		}
+
+		switch (req) {
+		case VHOST_USER_GET_FEATURES:
+			if (msg.size != sizeof(m.payload.u64)) {
+				PMD_DRV_LOG(ERR, "Received bad msg size.");
+				return -1;
+			}
+			*((__u64 *)arg) = msg.payload.u64;
+			break;
+		case VHOST_USER_GET_VRING_BASE:
+			if (msg.size != sizeof(m.payload.state)) {
+				PMD_DRV_LOG(ERR, "Received bad msg size.");
+				return -1;
+			}
+			memcpy(arg, &msg.payload.state,
+			       sizeof(struct vhost_vring_state));
+			break;
+		default:
+			PMD_DRV_LOG(ERR, "Received unexpected msg type.");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * Set up environment to talk with a vhost user backend.
+ * @param path
+ *   - The path to vhost user unix socket file.
+ *
+ * @return
+ *   - (-1) if fail to set up;
+ *   - (>=0) if successful, and it is the fd to vhostfd.
+ */
+int
+vhost_user_setup(const char *path)
+{
+	int fd;
+	int flag;
+	struct sockaddr_un un;
+
+	fd = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (fd < 0) {
+		PMD_DRV_LOG(ERR, "socket() error, %s", strerror(errno));
+		return -1;
+	}
+
+	flag = fcntl(fd, F_GETFD);
+	fcntl(fd, F_SETFD, flag | FD_CLOEXEC);
+
+	memset(&un, 0, sizeof(un));
+	un.sun_family = AF_UNIX;
+	snprintf(un.sun_path, sizeof(un.sun_path), "%s", path);
+	if (connect(fd, (struct sockaddr *)&un, sizeof(un)) < 0) {
+		PMD_DRV_LOG(ERR, "connect error, %s", strerror(errno));
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
-- 
2.1.4